Zobrazeno 1 - 5
of 5
pro vyhledávání: '"Kang, Peilin"'
Determining the kinetic bottlenecks that make transitions between metastable states difficult is key to understanding important physical problems like crystallization, chemical reactions, or protein folding. In all these phenomena, the system spends
Externí odkaz:
http://arxiv.org/abs/2401.05279
Recently, FGSM adversarial training is found to be able to train a robust model which is comparable to the one trained by PGD but an order of magnitude faster. However, there is a failure mode called catastrophic overfitting (CO) that the classifier
Externí odkaz:
http://arxiv.org/abs/2105.02942
Autor:
Kang P; Atomistic Simulations, Italian Institute of Technology, Genova, Italy., Trizio E; Atomistic Simulations, Italian Institute of Technology, Genova, Italy.; Department of Materials Science, Università di Milano-Bicocca, Milano, Italy., Parrinello M; Atomistic Simulations, Italian Institute of Technology, Genova, Italy. michele.parrinello@iit.it.
Publikováno v:
Nature computational science [Nat Comput Sci] 2024 Jun; Vol. 4 (6), pp. 451-460. Date of Electronic Publication: 2024 Jun 05.